Raport Lab5

Wczytanie danych

library(EDAWR)
library(dplyr)

Podsumowanie danych

head(tb)

## # A tibble: 6 × 6
##   country      year sex    child adult elderly
##   <chr>       <int> <chr>  <int> <int>   <int>
## 1 Afghanistan  1995 female    NA    NA      NA
## 2 Afghanistan  1995 male      NA    NA      NA
## 3 Afghanistan  1996 female    NA    NA      NA
## 4 Afghanistan  1996 male      NA    NA      NA
## 5 Afghanistan  1997 female     5    96       1
## 6 Afghanistan  1997 male       0    26       0

knitr::kable(summary(tb))

	country	year	sex	child	adult	elderly
	Length:3800	Min. :1995	Length:3800	Min. : 0.0	Min. : 0	Min. : 0.0
	Class :character	1st Qu.:1999	Class :character	1st Qu.: 25.0	1st Qu.: 1128	1st Qu.: 84.5
	Mode :character	Median :2004	Mode :character	Median : 76.0	Median : 2589	Median : 230.0
	NA	Mean :2004	NA	Mean : 493.2	Mean : 10864	Mean : 1253.0
	NA	3rd Qu.:2009	NA	3rd Qu.: 264.5	3rd Qu.: 6706	3rd Qu.: 640.0
	NA	Max. :2013	NA	Max. :25661.0	Max. :731540	Max. :125991.0
	NA	NA	NA	NA’s :396	NA’s :413	NA’s :413

Liczba zachorowań z podziałem na płeć

by_sex = group_by(tb, sex)
by_sex_summary <- summarize(by_sex, sum(c(child, adult, elderly), na.rm=TRUE))
by_sex_summary

## # A tibble: 2 × 2
##   sex    `sum(c(child, adult, elderly), na.rm = TRUE)`
##   <chr>                                          <int>
## 1 female                                      15656162
## 2 male                                        27062807

y <- unlist(by_sex_summary[2], use.names = FALSE)
sex_names <- unlist(by_sex_summary[1], use.names = FALSE)

barplot(y, names.arg = sex_names, ylab="Liczba zachorowań", xlab="Płeć")

Sumaryczna liczba zachorowań z podziałem na wiek

by_year = group_by(tb, year)

child_sum<-summarize(by_year, sum(child, na.rm=TRUE))
adult_sum<-summarize(by_year, sum(adult, na.rm=TRUE))
elderly_sum<-summarize(by_year, sum(elderly, na.rm=TRUE))

x <- unlist(elderly_sum[1], use.names = FALSE)
y_elderly <- unlist(elderly_sum[2], use.names = FALSE)
y_adult <- unlist(adult_sum[2], use.names = FALSE)
y_child <- unlist(child_sum[2], use.names = FALSE)
plot(x, y_adult, type='l', col="green", ylab="Liczba zachorowań", xlab="Lata", ylim=range(c(y_adult, y_child,y_elderly)))
lines(x, y_child, col="red")
lines(x, y_elderly, col="blue")

legend(x="topleft", fill=c("green", "red", "blue"), legend=c("Dorośli", "Dzieci", "Starsi"))

Sumaryczna liczba zachorowań z podziałem na wiek i kraje

countries <- unlist(tb["country"], use.names = FALSE)
countries <- countries[!duplicated(countries)]


for (cntr in countries) {
  country_tb <- filter(tb, country == cntr)


  by_year = group_by(country_tb, year)

  child_sum<-summarize(by_year, sum(child, na.rm=TRUE))
  adult_sum<-summarize(by_year, sum(adult, na.rm=TRUE))
  elderly_sum<-summarize(by_year, sum(elderly, na.rm=TRUE))

  x <- unlist(elderly_sum[1], use.names = FALSE)
  y_elderly <- unlist(elderly_sum[2], use.names = FALSE)
  y_adult <- unlist(adult_sum[2], use.names = FALSE)
  y_child <- unlist(child_sum[2], use.names = FALSE)
  plot(x, y_adult, type='l', col="green", ylab="Liczba zachorowań", xlab="Lata", ylim=range(c(y_adult, y_child,y_elderly)))
  lines(x, y_child, col="red")
  lines(x, y_elderly, col="blue")
  title(cntr)

  legend(x="topleft", fill=c("green", "red", "blue"), legend=c("Dorośli", "Dzieci", "Starsi"))
}